Week 4 · Deep dive · ~2 hours

Many Minds — every line, explained

One agent doing everything gets confused. A crew of specialists doesn't. Today you build a researcher → writer → critic pipeline and a tiny tree-of-thought, one line at a time.

👆 Tap a line → plain English 🔎 go deeper → extra detail # dim italics = a comment
Role
one agent, one job
Pipeline
output flows agent → agent
Hand-off
passing work to the next role
Branch
an idea to explore & score
Run it right here. Every cell runs in your browser. Run them in order, 1 → 4; they share memory. First Run downloads Python once (~10–15 MB).
Each agent here is a plain function with a role. In this file the “brains” are tiny stand-ins so it runs offline — but the structure (roles, hand-offs, scoring branches) is exactly what CrewAI and LangGraph give you. Swap each function's body for a real LLM call and you have a real crew.
↩ Back to Week 4 Week 5 deep dive →